cadence/breezewiki
2
4
Fork 4
Code Issues Pull requests 1 Releases Wiki Activity

Solr schema title can store numbers

Browse source
This commit is contained in:
Cadence Ember 2023-12-05 09:58:07 +13:00
parent 4f4fe91466
commit 4bf756bc9c
1 changed files with 17 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
archiver/solr-config-dir/schema.xml
View file

@ -83,40 +83,38 @@ https://solr.apache.org/guide/solr/latest/indexing-guide/document-analysis.html#
<fieldType name="text_prefix" class="solr.TextField" positionIncrementGap="100"> <fieldType name="text_prefix" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index"> <analyzer type="index">
<tokenizer class="solr.LowerCaseTokenizerFactory"/> <tokenizer name="standard"/>
<filter name="lowercase"/>
<filter class="solr.EdgeNGramFilterFactory" minGramSize="1" maxGramSize="20" /> <filter class="solr.EdgeNGramFilterFactory" minGramSize="1" maxGramSize="20" />
</analyzer> </analyzer>
<analyzer type="query"> <analyzer type="query">
<tokenizer class="solr.LowerCaseTokenizerFactory"/> <tokenizer name="standard"/>
<filter name="lowercase"/>
</analyzer> </analyzer>
</fieldType> </fieldType>
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true"> <fieldType name="text_en_splitting_numbers" class="solr.TextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index"> <analyzer type="index">
<tokenizer name="standard"/> <tokenizer name="whitespace"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/> <filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<!-- in this example, we will only use synonyms at query time <filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<filter name="lowercase"/> <filter name="lowercase"/>
<filter name="porterStem"/>
<filter name="flattenGraph" />
</analyzer> </analyzer>
<analyzer type="query"> <analyzer type="query">
<tokenizer name="standard"/> <tokenizer name="whitespace"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/> <filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/> <filter name="lowercase"/>
<filter name="porterStem"/>
</analyzer> </analyzer>
</fieldType> </fieldType>
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index"> <analyzer type="index">
<tokenizer name="whitespace"/> <tokenizer name="whitespace"/>
<!-- Case insensitive stop word removal. <filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
-->
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/> <filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/> <filter name="lowercase"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="(\d{2,})" replacement="" replace="all" /> <filter class="solr.PatternReplaceFilterFactory" pattern="(\d{2,})" replacement="" replace="all" />
@ -125,10 +123,7 @@ https://solr.apache.org/guide/solr/latest/indexing-guide/document-analysis.html#
</analyzer> </analyzer>
<analyzer type="query"> <analyzer type="query">
<tokenizer name="whitespace"/> <tokenizer name="whitespace"/>
<filter name="stop" <filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> <filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/> <filter name="lowercase"/>
<filter name="porterStem"/> <filter name="porterStem"/>
@ -137,7 +132,7 @@ https://solr.apache.org/guide/solr/latest/indexing-guide/document-analysis.html#
<!-- Fields --> <!-- Fields -->
<field name="id" type="string" indexed="true" required="true" /> <field name="id" type="string" indexed="true" required="true" />
<field name="title" type="text_en_splitting" indexed="true" stored="true" required="true" /> <field name="title" type="text_en_splitting_numbers" indexed="true" stored="true" required="true" />
<field name="body" type="text_en_splitting" indexed="true" stored="true" required="true" /> <field name="body" type="text_en_splitting" indexed="true" stored="true" required="true" />
<field name="table" type="text_en_splitting" indexed="true" stored="false" required="true" /> <field name="table" type="text_en_splitting" indexed="true" stored="false" required="true" />
<field name="len" type="pint" indexed="false" stored="true" required="true" /> <field name="len" type="pint" indexed="false" stored="true" required="true" />